© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49397
    Prev
    Next
    INDEX
    Explanations

    Next followed by sequentially ordered item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ultimately
    -0.08
     otherwise
    -0.08
    æľĢç»Ī以
    -0.07
    ä¸įè¿ĩæĿ¥
    -0.07
    æľĢç»Īè¿ĺæĺ¯
    -0.07
    /run
    -0.07
    ä¸Ģèµ·æĿ¥çľĭçľĭåIJ§
    -0.07
    æľĢç»Ī
    -0.07
     letztlich
    -0.07
    æľĢçµĤ
    -0.07
    POSITIVE LOGITS
    ä¹Łæĺ¯æľĢ
    0.08
    еÑĢÑĮ
    0.08
    çļĦéĹ®é¢ĺæĺ¯
    0.08
    士æŀĹ
    0.08
    è¦ģ注æĦıçļĦæĺ¯
    0.08
    ¢
    0.08
    ÑĮÑİ
    0.08
    ç¥ī
    0.07
     سرا
    0.07
    ×ķ׳×Ķ
    0.07
    Activations Density 0.008%

    No Known Activations